With the old model (and I suspect this one too) it's trained to generate from a single 'seed' pixel in the center of the image. If you erase the center of the image, that's when it completely collapses.

▲

oersted 4 hours ago | parent | next [-]

It must be more general than that, otherwise the cells wouldn’t be able to repair their area if the damage came from the wrong direction (repair is not center-out).

The model generally learns to generate each pixel from its surroundings, even if the surroundings are partially missing.

	▲	WhiteNoiz3 4 hours ago \| parent [-]
		There's hidden state in the model which presumably it uses to communicate position, ie there's the 3 colors but then a bunch of other channels that the model can use how it wants.

▲

cl3misch 4 hours ago | parent | prev [-]

Have you actually tried that? If you specifically erase the center, the image does change a lot at first, but rebuilds itself eventually (albeit to a slightly different final state). It's uncanny how "biological" is feels!

	▲	WhiteNoiz3 4 hours ago \| parent \| next [-]
		I have yes.. You need to erase a larger amount of the center, but it almost always results in a collapse wheras erasing around the center typically regrows.
	▲	Mithriil 4 hours ago \| parent \| prev [-]
		If you hold the eraser for a second at the center, I find that it destroys the image more often than not.